Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Python libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Resultado
    -0.07
    -learning
    -0.06
     reflective
    -0.06
    \\.
    -0.06
    kernel
    -0.06
    i
    -0.06
    DisplayName
    -0.06
    ClientId
    -0.06
    fak
    -0.06
     >
↵
    -0.06
    POSITIVE LOGITS
     قاب
    0.07
     comics
    0.07
     보호
    0.06
     Deletes
    0.06
     acidity
    0.06
    άνι
    0.06
    addOn
    0.06
    urally
    0.06
     RAT
    0.06
    doors
    0.06
    Act Density 0.008%

    No Known Activations